64-bit microprocessor roundup

I think I’ve already proclaimed 2003 to be the Year of MPEG-4 and the Year of recordable DVD. But did I mention that it’s also the Year of the 64-bit microprocessor? No? Okay, then…

A site called Real World Technologies just published the third in a series of technical roundups on 64-bit processors. If SPECfp_base2000 means something to you, you’ll probably find it an interesting read.

For my money, the most interesting story on the Wintel side of the world is how AMD forced Intel to change their 64-bit strategy. Intel originally tried to escape its x86 instruction set with Itanium (a.k.a. “Titanium”), which was not compatible with today’s 32-bit processors and would require new versions of all of your software (including your operating system). AMD saw Intel apparently giving up on the x86 franchise, and took the logical route of creating 64-bit extensions to the x86 instruction set (dubbed x86-64) for their 64-bit processor effort. Now, Intel has been forced to eat AMD’s dirty snow with an x86-64 processor of their own, and Itanium will find long-term success only on servers, if anywhere.

On the other side of the world, the great news for Mac users is that IBM’s PowerPC 970 — we’ll just call it the G5doesn’t suck. This thing’s going to come just in time:

The G4 and G4+ processors Apple currently uses in its Macintosh line of desktop and laptop computers are hopelessly out-muscled by the latest x86 processors from Intel and AMD. Worst yet, the growing use of [Intel’s] SSE [instructions] in multimedia and content creation software has put a slow leak in Apple’s competitive life preserver, the Altivec SIMD PowerPC instruction set extension. By some strange coincidence IBM has announced it was developing the PowerPC 970, a desktop class processor based on the POWER4 microarchitecture and extended with Altivec support.

Unfortunately, even if IBM can produce 2 GHz processors, the G5 will not be able to match the fastest Pentium 4 available right now.